© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 3474
    Prev
    Next
    INDEX
    Explanations

    mentions of legal proceedings or court hearings

    oai_token-act-pair · gpt-3.5-turbo

    references to formal proceedings or discussions, particularly involving hearings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jac
    -0.77
    rave
    -0.70
    romeda
    -0.67
     Univers
    -0.66
     Haram
    -0.63
     ejac
    -0.59
    obs
    -0.59
    football
    -0.58
     leaps
    -0.57
    oiler
    -0.57
    POSITIVE LOGITS
     examiner
    1.26
     convened
    1.03
     hearings
    1.02
     proceedings
    0.96
     testimony
    0.96
     transcripts
    0.95
     adjourn
    0.91
     chaired
    0.89
     hearing
    0.88
     held
    0.85
    Activations Density 0.046%

    No Known Activations